Novel Class Discovery: an Introduction and Key Concepts
- URL: http://arxiv.org/abs/2302.12028v1
- Date: Wed, 22 Feb 2023 10:07:01 GMT
- Title: Novel Class Discovery: an Introduction and Key Concepts
- Authors: Colin Troisemaine and Vincent Lemaire and St\'ephane Gosselin and
Alexandre Reiffers-Masson and Joachim Flocon-Cholet and Sandrine Vaton
- Abstract summary: Novel Class Discovery (NCD) is a growing field where we are given during training a labeled set of known classes and an unlabeled set of different classes that must be discovered.
In this paper, we provide a comprehensive survey of the state-of-the-art NCD methods.
- Score: 54.11148718494725
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Novel Class Discovery (NCD) is a growing field where we are given during
training a labeled set of known classes and an unlabeled set of different
classes that must be discovered. In recent years, many methods have been
proposed to address this problem, and the field has begun to mature. In this
paper, we provide a comprehensive survey of the state-of-the-art NCD methods.
We start by formally defining the NCD problem and introducing important
notions. We then give an overview of the different families of approaches,
organized by the way they transfer knowledge from the labeled set to the
unlabeled set. We find that they either learn in two stages, by first
extracting knowledge from the labeled data only and then applying it to the
unlabeled data, or in one stage by conjointly learning on both sets. For each
family, we describe their general principle and detail a few representative
methods. Then, we briefly introduce some new related tasks inspired by the
increasing number of NCD works. We also present some common tools and
techniques used in NCD, such as pseudo labeling, self-supervised learning and
contrastive learning. Finally, to help readers unfamiliar with the NCD problem
differentiate it from other closely related domains, we summarize some of the
closest areas of research and discuss their main differences.
Related papers
- Exclusive Style Removal for Cross Domain Novel Class Discovery [15.868889486516306]
Novel Class Discovery (NCD) is a promising field in open-world learning.
We introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features.
This module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions.
arXiv Detail & Related papers (2024-06-26T07:44:27Z) - Federated Learning for Generalization, Robustness, Fairness: A Survey
and Benchmark [55.898771405172155]
Federated learning has emerged as a promising paradigm for privacy-preserving collaboration among different parties.
We provide a systematic overview of the important and recent developments of research on federated learning.
arXiv Detail & Related papers (2023-11-12T06:32:30Z) - A Practical Approach to Novel Class Discovery in Tabular Data [38.41548083078336]
Novel Class Discovery (NCD) is a problem of extracting knowledge from a labeled set of known classes to accurately partition an unlabeled set of novel classes.
In this work, we propose to tune the hyper parameters of NCD methods by adapting the $k$-fold cross-validation process and hiding some of the known classes in each fold.
We find that the latent space of this method can be used to reliably estimate the number of novel classes.
arXiv Detail & Related papers (2023-11-09T15:24:44Z) - Recent Advances on Federated Learning: A Systematic Survey [3.6799810892671805]
Federated learning aims to achieve privacy-preserving collaborative learning among different parties.
We present a new taxonomy of federated learning in terms of the pipeline and challenges in federated scenarios.
We overview some prevalent federated learning frameworks and introduce their features.
arXiv Detail & Related papers (2023-01-03T14:19:03Z) - D\'ecouvrir de nouvelles classes dans des donn\'ees tabulaires [54.11148718494725]
In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes.
We show a way to extract knowledge from already known classes to guide the discovery process of novel classes in heterogeneous data.
arXiv Detail & Related papers (2022-11-28T09:48:55Z) - A Closer Look at Novel Class Discovery from the Labeled Set [13.31397670697559]
Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising disjoint but related classes.
We propose and substantiate the hypothesis that NCD could benefit more from a labeled set with a large degree of semantic similarity to the unlabeled set.
Specifically, we establish an extensive and large-scale benchmark with varying degrees of semantic similarity between labeled/unlabeled datasets on ImageNet.
arXiv Detail & Related papers (2022-09-19T15:41:44Z) - A Method for Discovering Novel Classes in Tabular Data [54.11148718494725]
In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes.
We show a way to extract knowledge from already known classes to guide the discovery process of novel classes in heterogeneous data.
arXiv Detail & Related papers (2022-09-02T11:45:24Z) - Prior Knowledge Guided Unsupervised Domain Adaptation [82.9977759320565]
We propose a Knowledge-guided Unsupervised Domain Adaptation (KUDA) setting where prior knowledge about the target class distribution is available.
In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound and Binary Relationship.
We propose a rectification module that uses such prior knowledge to refine model generated pseudo labels.
arXiv Detail & Related papers (2022-07-18T18:41:36Z) - A Unified Objective for Novel Class Discovery [48.1003877511578]
We introduce a UNified Objective function (UNO) for discovering novel classes.
UNO favors synergy between supervised and unsupervised learning.
Despite its simplicity, UNO outperforms the state of the art on several benchmarks.
arXiv Detail & Related papers (2021-08-19T07:22:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.